Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    mentions of specific regions or locations

    oai_token-act-pair · gpt-3.5-turbo

    geographical and demographic references in the context of conflict or social issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uted
    -0.59
    imens
    -0.56
    ibur
    -0.54
    iste
    -0.52
    Doctors
    -0.51
    onite
    -0.51
    Materials
    -0.50
    mand
    -0.49
    TPP
    -0.49
    laughs
    -0.48
    POSITIVE LOGITS
     &
    1.28
    /
    1.16
    /
    1.11
    &
    1.09
    terday
    0.96
     or
    0.87
     AND
    0.86
    /$
    0.80
     and
    0.79
    /_
    0.77
    Act Density 0.928%

    No Known Activations